Kernel Papers

The following are succinct summaries (kernels) of others’ research. These are not complete depictions; I focus on what I find insightful, interesting, surprising or novel.

Tessler and Goodman (PsyArXiv 2019)

Learning from Generic Language

Andrychowicz, ..., Bachem (ICLR 2021)

What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study

Dedieu, Gothoskar, et al. Dileep George (Arxiv 2019)

Learning higher-order sequential structure with cloned HMMs

Heald, Lengyel, Wolpert (Nature 2021)

Contextual inference underlies the learning of sensorimotor repertoires

Mattar and Daw (Nature Neuroscience 2018)

Prioritized memory access explains planning and hippocampal replay

Lin, Huh, Stauffer, Lim (NeurIPS 2021)

Learning to Ground Multi-Agent Communication with Autoencoders

Zhuang, Zhai, Yamins (ICCV 2019)

Local Aggregation for Unsupervised Learning of Visual Embeddings

Wu, Xiong, Yu and Lin (CVPR 2018)

Unsupervised Feature Learning via Non-Parametric Instance Discrimination

Caron, ..., Joulin (ICCV 2019)

Unsupervised Pre-Training of Image Features on Non-Curated Data

Caron, ..., Douze (ECCV 2019)

Deep Clustering for Unsupervised Learning of Visual Features

Hill, Cho, Korhonen, Bengio (ACL 2016)

Learning to Understand Phrases by Embedding the Dictionary

Tessler, Tsivids, Madeano, Harper and Tenenbaum (Arxiv 2021)

Growing knowledge culturally across generations to solve novel, complex tasks

Tessler, Bridgers, Tenenbaum (CogSci 2020)

How many observations is one generic worth?

Chopra, Tessler, Goodman (CogSci 2019)

The First Crank of the Cultural Ratchet

Liu, Tsai, Lee (KDD 2014)

Online Chinese Restaurant Process

Broderick, Boyd, Wibisono, Wilson (NeurIPS 2013)

Streaming Variational Bayes

Wang and Dunson (Journal of Computational and Graphical Statistics 2011)

Fast Bayesian Inference in Dirichlet Process Mixture Models

Nott, Zhang, Yau and Jasra (Journal of Computational and Graphical Statistics 2014)

A sequential algorithm for fast fitting of Dirichlet process mixture models

Gomes, Welling, Perona (CVPR 2008)

Incremental Learning of Nonparametric Bayesian Mixture Models

Ryan, Roy, Pignattelli, ..., Tonegawa (Science 2015)

Engram cells retain memory under retrograde amnesia

Ramirez and Liu, ..., Tonegawa (Science 2013)

Creating a False Memory in the Hippocampus

Monfils, ..., LeDoux (Science 2009)

Extinction-Reconsolidation Boundaries - Key to Persistent Attenuation of Fear Memories

Liu and Ramirez, ..., Tonegawa (Nature 2012)

Optogenetic stimulation of a hippocampal engram activates fear memory recall

Lau, ..., Josselyn (Neurobiology of Learning and Memory 2020)

The role of neuronal excitability, allocation to an engram and memory linking in the behavioral generation of a false memory in mice

Abdou, ..., Inokuchi (Science 2018)

Synapse-specific representation of the identity of overlapping memory engrams

Yokose, ..., Inokuchi (Science 2017)

Overlapping memory trace indispensable for linking, but not recalling, individual memories

Rashid, ..., Franklin, Josselyn (Science 2016)

Competition between engrams influences fear memory formation and recall

Cai, ..., Golshani, Silvia (Nature 2016)

A shared neural ensemble links distinct contextual memories encoded close in time

Blei, Jordan (Bayesian Analysis 2006)

Variational Inference for Dirichlet Process Mixtures

Pignatelli, ..., Tonegawa (Neuron 2019)

Engram Cell Excitability State Determines the Efficacy of Memory Retrieval

Fedus, Gelada, Bengio, Bellemare and Larochelle (Arxiv)

Hyperbolic Discounting and Learning over Multiple Horizons

Kulis and Jordan (ICML 2012)

Revisiting k-means - New Algorithms via Bayesian Nonparametrics

Rich, Liaw and Lee (Science 2014)

Large environments reveal the statistical structure governing hippocampal representations